Intelligent safety helmet and wearing detection method

Abstract

The invention provides an intelligent safety helmet and a wearing detection method, and the intelligent safety helmet comprises a safety helmet body, a human body detection module, a positioning module, a first image collection module, an impact prediction module, an environment detection module, a wearing detection module, and a controller. The first image acquisition module and the impact prediction module are arranged at the top of the safety helmet body, the environment detection module is arranged on the outer side of the safety helmet body, and the human body detection module, the wearing detection module and the controller are arranged on the inner side of the safety helmet body; the human body detection module, the positioning module, the first image acquisition module, the impact prediction module, the environment detection module and the wearing detection module are all electrically connected with the controller, and the controller is in communication connection with a background monitoring host through a wireless communication module. According to the intelligent safety helmet and the wearing detection method provided by the invention, wearing detection and obstacle detection of the safety helmet can be realized, and the safety of the construction process is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent safety helmets, in particular to an intelligent safety helmet and a wearing detection method. BACKGROUND

[0002] A safety helmet is a steel or similar material shallow dome hat worn to protect the head, which is a protective product to prevent impact objects from injuring the head. Most of the existing safety helmets do not have detection function, and cannot remind the user to avoid before the obstacle hits. In addition, the user often wears or does not wear the safety helmet in the use process, which may cause serious safety accidents. Therefore, it is necessary to design an intelligent safety helmet and a wearing detection method. SUMMARY

[0003] The purpose of the present application is to provide an intelligent safety helmet and a wearing detection method, which can realize the wearing detection and obstacle detection of the safety helmet, and improve the safety of the construction process.

[0004] To achieve the above purpose, the present application provides the following scheme:

[0005] An intelligent safety helmet and a wearing detection method, comprising: a safety helmet body, a human body detection module, a positioning module, a first image acquisition module, an impact prediction module, an environment detection module, a wearing detection module and a controller, the top of the safety helmet body is provided with the first image acquisition module and the impact prediction module, the outer side of the safety helmet body is provided with the environment detection module, the inner side of the safety helmet body is provided with the human body detection module, the wearing detection module and the controller, the human body detection module, the positioning module, the first image acquisition module, the impact prediction module, the environment detection module and the wearing detection module are electrically connected with the controller, and the controller is communicated with a background monitoring host through a wireless communication module;

[0006] The human body detection module is used for detecting human life characteristics, including body temperature, heart rate blood oxygen, blood pressure and respiratory rate;

[0007] The positioning module is used for acquiring the positioning of the safety helmet body;

[0008] The first image acquisition module is used for acquiring the image on the top of the safety helmet body;

[0009] The impact prediction module is used for impact prediction according to the image acquired by the first image acquisition module;

[0010] The wearing detection module is used for detecting whether the safety helmet is normally worn;

[0011] The environment detection module is used for detecting the environment of the safety helmet body.

[0012] Optionally, the impact prediction module includes a radar probe and a prediction processing module, wherein the radar probe and the prediction processing module are electrically connected to the controller.

[0013] Optionally, the wearing detection module includes a light-sensing sensor, a second image acquisition module, a model generation module, a model training module, and a processing module. The light-sensing sensor is located on the top of the helmet body. Multiple second image acquisition modules are evenly arranged near the working area to acquire images of the user wearing the helmet body. The model generation module is used to generate a detection model. The model training module is used to train the model. The processing module is used to input the images acquired by the second image acquisition modules into the trained model to achieve wearing detection. The light-sensing sensor is electrically connected to the controller. The second image acquisition module, the model generation module, the model training module, and the processing module are connected to the background monitoring host.

[0014] Optionally, an alarm device is also provided on the outside of the helmet body, and the alarm device is electrically connected to the controller.

[0015] The present invention also provides a smart helmet wearing detection method, applied to the aforementioned smart helmet, characterized by comprising the following steps:

[0016] Step 1: Detect the environment in which the safety helmet is located using the environmental detection module;

[0017] Step 2: Accident prediction of the safety helmet is achieved through the first image acquisition module and the impact prediction module;

[0018] Step 3: Detect the wearing of the safety helmet using the positioning module and the wearing detection module.

[0019] Optionally, in step 2, the impact prediction of the safety helmet is achieved through the first image acquisition module and the impact prediction module, specifically as follows:

[0020] The radar probe detects whether there is an obstacle on the top of the safety helmet. If there is no obstacle, no action is taken. If there is an obstacle, the controller controls the first image acquisition module to acquire an image of the obstacle and sends it to the prediction processing module. The prediction processing module determines the probability of the obstacle using a preset obstacle detection model. If the probability is greater than a preset threshold, the controller controls the alarm device to sound an alarm. Otherwise, no action is taken.

[0021] Optionally, in step 3, the wearing detection of the safety helmet is performed through the positioning module and the wearing detection module, specifically as follows:

[0022] The light-sensing sensor detects whether the helmet is being worn on the user's head. If not, the controller obtains the user's information about the helmet and sends it to the backend monitoring host.

[0023] If worn, the positioning module obtains the location information of the helmet and sends it to the backend monitoring host. The backend monitoring host collects images near the helmet using the second image acquisition module at fixed intervals based on the helmet's location information. The backend monitoring host controls the model generation module to generate a detection model and controls the model training module to train the model using a preset dataset. The trained detection model and the images collected by the second image acquisition module are sent to the processing module. The processing module inputs the images into the detection model to obtain the wearing result. The backend monitoring host sends corresponding instructions to the controller based on the wearing result.

[0024] Optionally, the detection model is an improved SSD model, wherein the features extracted from the first three layers of the traditional SSD model are input into the first Conv-LSTM model, and the features extracted from the last three layers of the traditional SSD model are input into the second Conv-LSTM model.

[0025] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: The intelligent safety helmet and wearing detection method provided by the present invention include a safety helmet body, a human body detection module, a positioning module, a first image acquisition module, an impact prediction module, an environmental detection module, a wearing detection module, and a controller. The human body detection module detects human vital signs, including body temperature, heart rate, blood oxygen saturation, blood pressure, and respiratory rate. The positioning module acquires the positioning of the safety helmet body. The first image acquisition module acquires an image of the top of the safety helmet body. The impact prediction module performs impact prediction based on the image acquired by the first image acquisition module. The wearing detection module detects whether the safety helmet is worn correctly. The environmental detection module detects the environment in which the safety helmet body is located. The method includes detecting the environment in which the safety helmet body is located through the environmental detection module, performing impact prediction of the safety helmet through the first image acquisition module and the impact prediction module, and performing wearing detection of the safety helmet through the positioning module and the wearing detection module. This intelligent safety helmet and method can achieve both safety helmet wearing detection and obstacle detection, improving the safety of the construction process. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a structural block diagram of a smart safety helmet provided in an embodiment of the present invention;

[0028] Figure 2 This is a schematic diagram of the smart safety helmet wearing detection method according to an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of the improved SSD model framework. Detailed Implementation

[0030] The purpose of this invention is to provide an intelligent safety helmet and a wearing detection method, which can realize the wearing detection of safety helmets and obstacle detection, thereby improving the safety of the construction process and increasing the recognition efficiency.

[0031] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] like Figure 1 As shown, the smart safety helmet provided in this embodiment of the invention includes: a helmet body, a human body detection module, a positioning module, a first image acquisition module, an impact prediction module, an environmental detection module, a wearing detection module, and a controller. The first image acquisition module and the impact prediction module are disposed on the top of the helmet body, the environmental detection module is disposed on the outer side of the helmet body, and the human body detection module, the wearing detection module, and the controller are disposed on the inner side of the helmet body. The human body detection module, the positioning module, the first image acquisition module, the impact prediction module, the environmental detection module, and the wearing detection module are all electrically connected to the controller. The controller is communicatively connected to a background monitoring host through a wireless communication module.

[0033] The human body detection module is used to detect human vital signs, including body temperature, heart rate, blood oxygen, blood pressure, and respiratory rate.

[0034] The positioning module is used to collect the positioning of the helmet body. The positioning module can use a Beidou positioning chip. In addition, the present invention provides an embodiment in which an accelerometer is added to collect acceleration data. The acceleration data and the latitude, longitude and altitude located by the Beidou positioning chip can be used to determine whether the user has fallen.

[0035] The first image acquisition module is used to acquire an image of the top of the safety helmet body;

[0036] The impact prediction module is used to predict impacts based on images acquired by the first image acquisition module.

[0037] The helmet wearing detection module is used to detect whether the helmet is worn properly.

[0038] The environmental detection module is used to detect the environment of the helmet body, such as wind speed, air pressure, temperature, humidity, etc.

[0039] The present invention can also be equipped with additional communication devices, such as speakers and microphones, to enable communication with the background monitoring host.

[0040] Both the first image acquisition module and the second image acquisition module can use conventional cameras.

[0041] The impact prediction module includes a radar probe and a prediction processing module, which are electrically connected to the controller.

[0042] The wearing detection module includes a light-sensing sensor, a second image acquisition module, a model generation module, a model training module, and a processing module. The light-sensing sensor is located on the top of the helmet body. Multiple second image acquisition modules are evenly arranged near the working area to acquire images of the user wearing the helmet body. The model generation module is used to generate a detection model. The model training module is used to train the model. The processing module is used to input the images acquired by the second image acquisition modules into the trained model to achieve wearing detection. The light-sensing sensor is electrically connected to the controller. The second image acquisition module, the model generation module, the model training module, and the processing module are connected to the background monitoring host.

[0043] This invention provides an embodiment of a light-sensing detection sensor, which can employ the AP3426 light-sensing detection chip.

[0044] An alarm device is also provided on the outside of the helmet body, and the alarm device is electrically connected to the controller.

[0045] like Figure 2 As shown, the present invention also provides a smart helmet wearing detection method, applied to the above-mentioned smart helmet, comprising the following steps:

[0046] Step 1: Detect the environment in which the safety helmet is located using the environmental detection module;

[0047] Step 2: Accident prediction of the safety helmet is achieved through the first image acquisition module and the impact prediction module;

[0048] Step 3: Detect the wearing of the safety helmet using the positioning module and the wearing detection module.

[0049] In step 2, the impact prediction of the safety helmet is achieved through the first image acquisition module and the impact prediction module, specifically as follows:

[0050] The radar probe detects whether there is an obstacle on the top of the safety helmet. If there is no obstacle, no action is taken. If there is an obstacle, the controller controls the first image acquisition module to acquire an image of the obstacle and sends it to the prediction processing module. The prediction processing module determines the probability of the obstacle using a preset obstacle detection model. If the probability is greater than a preset threshold, the controller controls the alarm device to sound an alarm. Otherwise, no action is taken.

[0051] The preset obstacle detection model construction steps are as follows: A planar coordinate system is established on the ground. The obstacle's coordinates on the ground are marked as A through image position recognition. The user's coordinates on the ground are marked as D based on the collected positioning information. The obstacle's impact point E is calculated. The collected wind force is marked as C. If C is less than the preset wind force value, the impact point E is point A. If C is greater than or equal to the preset wind force value, the wind direction is marked as B. The position of the impact point E is calculated. Point E is located in the direction of B from point A, and the distance between point E and point A is (C / preset wind force value) * preset offset value. The straight-line distance between point D and the impact point E is calculated and marked as L. If L is greater than or equal to the preset safety distance, the detection result is output as an obstacle exists but will not hit the user. If L is less than the preset safety distance, the detection result is output as an obstacle exists and there is a chance it will hit the user. The probability of the obstacle hitting the user is calculated and output. If the probability is greater than a preset threshold, the controller activates the alarm device. Otherwise, the probability of hitting the user is played through a speaker to remind the user.

[0052] In step 3, the wearing of the safety helmet is detected using the positioning module and the wearing detection module, specifically as follows:

[0053] The light-sensing sensor detects whether the helmet is being worn on the user's head. If not, the controller obtains the user's information about the helmet and sends it to the backend monitoring host.

[0054] If worn, the positioning module obtains the location information of the safety helmet and sends it to the backend monitoring host. The backend monitoring host collects images near the safety helmet at fixed intervals based on the location information of the safety helmet. The backend monitoring host controls the model generation module to generate a detection model and controls the model training module to train the model using a preset dataset. The trained detection model and the images collected by the second image acquisition module are sent to the processing module. The processing module inputs the images into the detection model to obtain the wearing result. The backend monitoring host sends corresponding instructions to the controller based on the wearing result. The preset dataset consists of images collected at the construction site, which are then labeled to obtain the dataset.

[0055] The detection model is an improved SSD model. Features extracted from the first three layers of the traditional SSD model are input into a first Conv-LSTM model, while features extracted from the last three layers of the traditional SSD model are input into a second Conv-LSTM model. The improved SSD model framework is as follows: Figure 3 As shown.

[0056] The present invention provides an intelligent safety helmet and a method for detecting its wearing. The intelligent safety helmet includes a helmet body, a human body detection module, a positioning module, a first image acquisition module, an impact prediction module, an environmental detection module, a wearing detection module, and a controller. The human body detection module detects human vital signs, including body temperature, heart rate, blood oxygen saturation, blood pressure, and respiratory rate. The positioning module acquires the location of the safety helmet body. The first image acquisition module acquires an image of the top of the safety helmet body. The impact prediction module performs impact prediction based on the image acquired by the first image acquisition module. The wearing detection module detects whether the safety helmet is being worn correctly. The environmental detection module detects the environment in which the safety helmet body is located. The method includes detecting the environment in which the safety helmet body is located using the environmental detection module, predicting impacts using the first image acquisition module and the impact prediction module, and detecting the wearing of the safety helmet using the positioning module and the wearing detection module. This intelligent safety helmet and method can achieve both helmet wearing detection and obstacle detection, improving the safety of the construction process.

[0057] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A smart safety helmet, characterized in that, include: The system includes a safety helmet body, a human body detection module, a positioning module, a first image acquisition module, an impact prediction module, an environmental detection module, a wearing detection module, and a controller. The first image acquisition module and the impact prediction module are located on the top of the safety helmet body. The environmental detection module is located on the outer side of the safety helmet body. The human body detection module, the positioning module, the first image acquisition module, the impact prediction module, the environmental detection module, and the wearing detection module are located on the inner side of the safety helmet body. The human body detection module, the positioning module, the first image acquisition module, the impact prediction module, the environmental detection module, and the wearing detection module are all electrically connected to the controller. The controller is connected to a background monitoring host via a wireless communication module. The human body detection module is used to detect human vital signs, including body temperature, heart rate, blood oxygen, blood pressure, and respiratory rate. The positioning module is used to collect the positioning data of the helmet body; The first image acquisition module is used to acquire an image of the top of the safety helmet body; The impact prediction module is used to predict impacts based on images acquired by the first image acquisition module. The helmet wearing detection module is used to detect whether the helmet is worn properly. The environmental detection module is used to detect the environment surrounding the helmet.

2. The smart safety helmet according to claim 1, characterized in that, The impact prediction module includes a radar probe and a prediction processing module, which are electrically connected to the controller.

3. The smart safety helmet according to claim 1, characterized in that, The wearing detection module includes a light-sensing sensor, a second image acquisition module, a model generation module, a model training module, and a processing module. The light-sensing sensor is located on the top of the helmet body. Multiple second image acquisition modules are evenly arranged near the working area to acquire images of the user wearing the helmet body. The model generation module is used to generate a detection model. The model training module is used to train the model. The processing module is used to input the images acquired by the second image acquisition modules into the trained model to achieve wearing detection. The light-sensing sensor is electrically connected to the controller. The second image acquisition module, the model generation module, the model training module, and the processing module are connected to the background monitoring host.

4. The smart safety helmet according to claim 1, characterized in that, An alarm device is also provided on the outside of the helmet body, and the alarm device is electrically connected to the controller.

5. A method for detecting the wearing of a smart safety helmet, applied to the smart safety helmet described in any one of claims 1-4, characterized in that, Includes the following steps: Step 1: Detect the environment in which the safety helmet is located using the environmental detection module; Step 2: Accident prediction of the safety helmet is achieved through the first image acquisition module and the impact prediction module; Step 3: Detect the wearing of the safety helmet using the positioning module and the wearing detection module.

6. The intelligent safety helmet wearing detection method according to claim 5, characterized in that, In step 2, the impact prediction of the safety helmet is achieved through the first image acquisition module and the impact prediction module, specifically as follows: The radar probe detects whether there is an obstacle on the top of the safety helmet. If there is no obstacle, no action is taken. If there is an obstacle, the controller controls the first image acquisition module to acquire an image of the obstacle and sends it to the prediction processing module. The prediction processing module determines the probability of the obstacle using a preset obstacle detection model. If the probability is greater than a preset threshold, the controller controls the alarm device to sound an alarm. Otherwise, no action is taken.

7. The intelligent safety helmet wearing detection method according to claim 6, characterized in that, In step 3, the wearing of the safety helmet is detected using the positioning module and the wearing detection module, specifically as follows: The light-sensing sensor detects whether the helmet is being worn on the user's head. If not, the controller obtains the user's information about the helmet and sends it to the backend monitoring host. If worn, the positioning module obtains the location information of the helmet and sends it to the backend monitoring host. The backend monitoring host collects images near the helmet using the second image acquisition module at fixed intervals based on the helmet's location information. The backend monitoring host controls the model generation module to generate a detection model and controls the model training module to train the model using a preset dataset. The trained detection model and the images collected by the second image acquisition module are sent to the processing module. The processing module inputs the images into the detection model to obtain the wearing result. The backend monitoring host sends corresponding instructions to the controller based on the wearing result.

8. The intelligent safety helmet wearing detection method according to claim 7, characterized in that, The detection model is an improved SSD model, in which the features extracted from the first three layers of the traditional SSD model are input into the first Conv-LSTM model, and the features extracted from the last three layers of the traditional SSD model are input into the second Conv-LSTM model.

Images